Update app.py

app.py

@@ -2,52 +2,64 @@ import torch
 import cv2
 import numpy as np
 import gradio as gr
-from PIL import Image
 import random
 
+# Load YOLOv5 model
 device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
-
-# Use a smaller model for faster inference
-model = torch.hub.load('ultralytics/yolov5', 'yolov5s', pretrained=True).to(device)
+model = torch.hub.load('ultralytics/yolov5', 'yolov5x', pretrained=True).to(device)
 model.eval()
 
+# Use half-precision if CUDA is available
+if device.type == 'cuda':
+    model.half()
+
+# Get class names
 CLASS_NAMES = model.names  
-random.seed(42)
-CLASS_COLORS = {cls: (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255)) for cls in CLASS_NAMES}
 
-def preprocess_image(image):
-    image = Image.fromarray(image).convert("RGB").resize((640, 640))
-    return image
+# Assign random colors for each class
+CLASS_COLORS = {cls: (random.randint(0, 255), random.randint(0, 255), random.randint(0, 255)) for cls in CLASS_NAMES}
 
 def detect_objects(image):
-    image = preprocess_image(image)
+    """Detect objects in an image using YOLOv5 with optimized inference speed."""
+    image = cv2.cvtColor(image, cv2.COLOR_RGB2BGR)  # Convert to BGR for OpenCV
+    img_resized = cv2.resize(image, (640, 640))  # Resize for faster processing
+    img_tensor = torch.from_numpy(img_resized).to(device).float() / 255.0  # Normalize
+    img_tensor = img_tensor.permute(2, 0, 1).unsqueeze(0)  # Convert to batch format
 
-    results = model([image])  # Batch processing for efficiency
+    if device.type == 'cuda':
+        img_tensor = img_tensor.half()  # Use half precision for speed
 
-    image = np.array(image)  
-    
-    for *box, conf, cls in results.xyxy[0]:  
-        x1, y1, x2, y2 = map(int, box)
-        class_name = CLASS_NAMES[int(cls)]  
-        confidence = conf.item() * 100  
+    # Run model inference
+    with torch.no_grad():
+        results = model(img_tensor)
+
+    detections = results.xyxy[0].cpu().numpy()
+
+    for x1, y1, x2, y2, conf, cls in detections:
+        x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
+        class_name = CLASS_NAMES[int(cls)]
+        confidence = conf * 100
 
         color = CLASS_COLORS[class_name]
 
-        cv2.rectangle(image, (x1, y1), (x2, y2), color, 4)  
+        # Draw bounding box
+        cv2.rectangle(image, (x1, y1), (x2, y2), color, 3)
+
+        # Label
         label = f"{class_name} ({confidence:.1f}%)"
-        cv2.putText(image, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 
-                    1, color, 3, cv2.LINE_AA)
+        cv2.putText(image, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.8, color, 2)
 
-    return image
+    return cv2.cvtColor(image, cv2.COLOR_BGR2RGB)  # Convert back to RGB for Gradio
 
+# Gradio Interface
 iface = gr.Interface(
     fn=detect_objects,
     inputs=gr.Image(type="numpy", label="Upload Image"),
     outputs=gr.Image(type="numpy", label="Detected Objects"),
-    title="Object Detection with YOLOv5",
-    description="Use webcam or upload an image to detect objects.",
-    allow_flagging="never",
-    examples=["examples/spring_street_after.jpg", "examples/pexels-hikaique-109919.jpg"]
+    title="Fast Object Detection with YOLOv5",
+    description="Use webcam or upload an image for object detection results.",
+    allow_flagging="never"
 )
 
+# Launch the app
 iface.launch()